The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes run_shell_command, providing a broad interface for executing system commands. This is intended for preparing and auditing materials but represents a significant capability level.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and audit external due diligence materials (contracts, equity documents, financials). Processing these untrusted inputs in conjunction with tools like run_shell_command and write_file creates a surface where adversarial instructions hidden in documents could attempt to influence the agent's behavior.
[DATA_EXPOSURE]: The skill is explicitly designed to handle highly sensitive data, including founder-context.md, capitalization tables, equity agreements, and financial records. Although the instructions include PII redaction protocols, the inherent access to these files is a critical part of the skill's risk profile.

data-room